🎴 Flashcard Mode
Machine Learning Policy Gradients
Card1 / 15
Mastered0
Review0
QuestionClick to flip
What is the primary goal of policy gradient methods in machine learning?
AnswerClick to flip back
A
To optimize the parameters of a policy network
💡 Explanation:
Policy gradient methods aim to optimize the parameters of a policy network to maximize the expected reward or minimize the expected cost of the agent's actions in a given environment.